def test_assignment():
X = numpy.array([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0], [7.0, 8.0, 9.0]])
M = numpy.array([[1, 1, 0], [0, 1, 0], [1, 1, 1]])
K = 2
kmeans = KMeans(X, M, K)
# Test change - new closest clusters are [0,0,1] - see test_closest_cluster
centroids = [[1.0, 3.0, 1.0], [2.0, 1.0, 3.0]]
mask_centroids = [[0, 1, 1], [1, 1, 0]]
cluster_assignments = [0, 1, 1]
kmeans.centroids = centroids
kmeans.mask_centroids = mask_centroids
kmeans.cluster_assignments = cluster_assignments
change = kmeans.assignment()
assert change == True
assert numpy.array_equal([0, 0, 1], kmeans.cluster_assignments)
assert numpy.array_equal([[0, 1], [2]], kmeans.data_point_assignments)
# Test no change
centroids = [[1.0, 3.0, 1.0], [2.0, 1.0, 3.0]]
mask_centroids = [[0, 1, 1], [1, 1, 0]]
cluster_assignments = [0, 0, 1]
kmeans.centroids = centroids
kmeans.mask_centroids = mask_centroids
kmeans.cluster_assignments = cluster_assignments
change = kmeans.assignment()
assert change == False
assert numpy.array_equal([0, 0, 1], kmeans.cluster_assignments)
assert numpy.array_equal([[0, 1], [2]], kmeans.data_point_assignments)
def test_assignment():
X = numpy.array([[1.0,2.0,3.0],[4.0,5.0,6.0],[7.0,8.0,9.0]])
M = numpy.array([[1,1,0],[0,1,0],[1,1,1]])
K = 2
kmeans = KMeans(X,M,K)
# Test change - new closest clusters are [0,0,1] - see test_closest_cluster
centroids = [[1.0,3.0,1.0],[2.0,1.0,3.0]]
mask_centroids = [[0,1,1],[1,1,0]]
cluster_assignments = [0,1,1]
kmeans.centroids = centroids
kmeans.mask_centroids = mask_centroids
kmeans.cluster_assignments = cluster_assignments
change = kmeans.assignment()
assert change == True
assert numpy.array_equal([0,0,1],kmeans.cluster_assignments)
assert numpy.array_equal([[0,1],[2]],kmeans.data_point_assignments)
# Test no change
centroids = [[1.0,3.0,1.0],[2.0,1.0,3.0]]
mask_centroids = [[0,1,1],[1,1,0]]
cluster_assignments = [0,0,1]
kmeans.centroids = centroids
kmeans.mask_centroids = mask_centroids
kmeans.cluster_assignments = cluster_assignments
change = kmeans.assignment()
assert change == False
assert numpy.array_equal([0,0,1],kmeans.cluster_assignments)
assert numpy.array_equal([[0,1],[2]],kmeans.data_point_assignments)
def test_closest_cluster():
X = numpy.array([[1.0,2.0,3.0],[4.0,5.0,6.0],[7.0,8.0,9.0]])
M = numpy.array([[1,1,0],[0,1,0],[1,1,1]])
K = 2
kmeans = KMeans(X,M,K)
# Equal distance for point 0
centroids = [[1.0,3.0,1.0],[2.0,1.0,3.0]]
mask_centroids = [[0,1,1],[1,1,0]]
kmeans.centroids = centroids
kmeans.mask_centroids = mask_centroids
expected_closest_cluster_0 = 0 # MSE = 1.0 vs 1.0
expected_closest_cluster_1 = 0 # MSE = 4.0 vs 16.0
expected_closest_cluster_2 = 1 # MSE = 44.5 vs 37.0
closest_cluster_0 = kmeans.closest_cluster(X[0],0,M[0])
closest_cluster_1 = kmeans.closest_cluster(X[1],1,M[1])
closest_cluster_2 = kmeans.closest_cluster(X[2],2,M[2])
assert expected_closest_cluster_0 == closest_cluster_0
assert expected_closest_cluster_1 == closest_cluster_1
assert expected_closest_cluster_2 == closest_cluster_2
# Also test whether the distances are set correctly
expected_distances = [1.0,4.0,37.0]
distances = kmeans.distances
assert numpy.array_equal(expected_distances,distances)
# Test when all MSEs return None (impossible but still testing behaviour)
centroids = numpy.ones((2,3))
mask_centroids = [[0,0,1],[0,0,0]]
kmeans.centroids = centroids
kmeans.mask_centroids = mask_centroids
expected_closest_cluster = 1
closest_cluster = kmeans.closest_cluster(X[0],0,M[0])
assert expected_closest_cluster == closest_cluster
def test_closest_cluster():
X = numpy.array([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0], [7.0, 8.0, 9.0]])
M = numpy.array([[1, 1, 0], [0, 1, 0], [1, 1, 1]])
K = 2
kmeans = KMeans(X, M, K)
# Equal distance for point 0
centroids = [[1.0, 3.0, 1.0], [2.0, 1.0, 3.0]]
mask_centroids = [[0, 1, 1], [1, 1, 0]]
kmeans.centroids = centroids
kmeans.mask_centroids = mask_centroids
expected_closest_cluster_0 = 0 # MSE = 1.0 vs 1.0
expected_closest_cluster_1 = 0 # MSE = 4.0 vs 16.0
expected_closest_cluster_2 = 1 # MSE = 44.5 vs 37.0
closest_cluster_0 = kmeans.closest_cluster(X[0], 0, M[0])
closest_cluster_1 = kmeans.closest_cluster(X[1], 1, M[1])
closest_cluster_2 = kmeans.closest_cluster(X[2], 2, M[2])
assert expected_closest_cluster_0 == closest_cluster_0
assert expected_closest_cluster_1 == closest_cluster_1
assert expected_closest_cluster_2 == closest_cluster_2
# Also test whether the distances are set correctly
expected_distances = [1.0, 4.0, 37.0]
distances = kmeans.distances
assert numpy.array_equal(expected_distances, distances)
# Test when all MSEs return None (impossible but still testing behaviour)
centroids = numpy.ones((2, 3))
mask_centroids = [[0, 0, 1], [0, 0, 0]]
kmeans.centroids = centroids
kmeans.mask_centroids = mask_centroids
expected_closest_cluster = 1
closest_cluster = kmeans.closest_cluster(X[0], 0, M[0])
assert expected_closest_cluster == closest_cluster
def test_find_point_furthest_away():
X = numpy.array([[1.0,2.0,3.0],[4.0,5.0,6.0],[7.0,8.0,9.0]])
M = numpy.array([[1,1,0],[0,1,0],[1,1,1]])
K = 2
kmeans = KMeans(X,M,K)
# Equal distance for point 0
centroids = [[1.0,3.0,1.0],[2.0,1.0,3.0]]
mask_centroids = [[0,1,1],[1,1,0]]
kmeans.centroids = centroids
kmeans.mask_centroids = mask_centroids
kmeans.closest_cluster(X[0],0,M[0]) # MSE = 1.0 vs 1.0
kmeans.closest_cluster(X[1],1,M[1]) # MSE = 4.0 vs 16.0
kmeans.closest_cluster(X[2],2,M[2]) # MSE = 44.5 vs 37.0
expected_furthest_away = 2
furthest_away = kmeans.find_point_furthest_away()
assert expected_furthest_away == furthest_away
def test_find_point_furthest_away():
X = numpy.array([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0], [7.0, 8.0, 9.0]])
M = numpy.array([[1, 1, 0], [0, 1, 0], [1, 1, 1]])
K = 2
kmeans = KMeans(X, M, K)
# Equal distance for point 0
centroids = [[1.0, 3.0, 1.0], [2.0, 1.0, 3.0]]
mask_centroids = [[0, 1, 1], [1, 1, 0]]
kmeans.centroids = centroids
kmeans.mask_centroids = mask_centroids
kmeans.closest_cluster(X[0], 0, M[0]) # MSE = 1.0 vs 1.0
kmeans.closest_cluster(X[1], 1, M[1]) # MSE = 4.0 vs 16.0
kmeans.closest_cluster(X[2], 2, M[2]) # MSE = 44.5 vs 37.0
expected_furthest_away = 2
furthest_away = kmeans.find_point_furthest_away()
assert expected_furthest_away == furthest_away
def test_update():
# Normal case
X = numpy.array([[1.0,2.0,3.0],[4.0,5.0,6.0],[7.0,8.0,9.0]])
M = numpy.array([[1,1,0],[0,1,0],[1,1,1]])
K = 2
kmeans = KMeans(X,M,K)
kmeans.data_point_assignments = numpy.array([[0,1],[2]]) #points 0,1 to cluster 0, point 2 to cluster 1
kmeans.centroids = [[0.0,0.0,0.0],[0.0,0.0,0.0]]
kmeans.mask_centroids = [[0.0,0.0,0.0],[0.0,0.0,0.0]]
new_centroids = [[1.0,3.5,0],[7.0,8.0,9.0]]
new_mask_centroids = [[1,1,0],[1,1,1]]
kmeans.update()
assert numpy.array_equal(new_centroids,kmeans.centroids)
assert numpy.array_equal(new_mask_centroids,kmeans.mask_centroids)
# Case when one cluster has no points assigned to it - we then randomly re-initialise that cluster
X = numpy.array([[1.0,2.0,3.0],[4.0,5.0,6.0],[7.0,8.0,9.0]])
M = numpy.array([[1,1,0],[0,1,0],[1,1,1]])
K = 2
kmeans = KMeans(X,M,K,'random')
kmeans.data_point_assignments = numpy.array([[0,1,2],[]]) #points 0,1,2 to cluster 0, none to cluster 1
kmeans.centroids = [[0.0,0.0,0.0],[0.0,0.0,0.0]]
kmeans.mask_centroids = [[0.0,0.0,0.0],[0.0,0.0,0.0]]
kmeans.mins = [1.0,2.0,9.0]
kmeans.maxs = [7.0,8.0,9.0]
new_centroids = [[4.0,5.0,9.0],[6.066531109150288,6.547726417641815,9.0]]
new_mask_centroids = [[1,1,1],[1,1,1]]
random.seed(0)
kmeans.update()
assert numpy.array_equal(new_centroids,kmeans.centroids)
assert numpy.array_equal(new_mask_centroids,kmeans.mask_centroids)
# Case when we use the 'singleton' option for empty clusters - reassign point furthest away to the cluster
# Points 0 and 1 go to cluster 0, 2 to cluster 1 and none to cluster 2.
# Point 2 is furthest away, so gets reassigned to cluster 2 - making
# cluster 1 empty. Then point 1 is furthest away and gets reassigned to cluster 1
X = numpy.array([[1.0,2.0,3.0],[4.0,5.0,6.0],[7.0,8.0,9.0]])
M = numpy.array([[1,1,0],[0,1,0],[1,1,1]])
K = 3
kmeans = KMeans(X,M,K,resolve_empty='singleton')
kmeans.data_point_assignments = numpy.array([[0,1],[2],[]]) #points 0,1 to cluster 0, 2 to cluster 1, none to cluster 2
kmeans.cluster_assignments = [0,0,1]
kmeans.centroids = [[1.0,2.0,3.0],[15.0,16.0,17.0],[500.0,500.0,500.0]]
kmeans.mask_centroids = [[1,1,0],[1,1,1],[1,1,1]]
kmeans.distances = numpy.array([
kmeans.compute_MSE(kmeans.X[0],kmeans.centroids[0],M[0],kmeans.mask_centroids[0]),
kmeans.compute_MSE(kmeans.X[1],kmeans.centroids[0],M[1],kmeans.mask_centroids[0]),
kmeans.compute_MSE(kmeans.X[2],kmeans.centroids[1],M[2],kmeans.mask_centroids[1])
])
kmeans.mins = [1.0,2.0,9.0]
kmeans.maxs = [7.0,8.0,9.0]
new_centroids = [[1.0,2.0,0],[4.0,5.0,6.0],[7.0,8.0,9.0]]
new_data_point_assignments = [[0],[1],[2]]
new_distances = [0,0,0]
kmeans.update()
assert new_data_point_assignments == list(kmeans.data_point_assignments)
assert numpy.array_equal(new_distances,kmeans.distances)
assert numpy.array_equal(new_centroids,kmeans.centroids)
def test_cluster():
### No missing values case.
# Points 1,2 will first go to cluster 2, and point 3 to cluster 1.
# Then point 1 will switch to cluster 1.
X = [[2,5],[7,5],[2,3]]
M = numpy.ones((3,2))
K = 2
kmeans = KMeans(X,M,K)
kmeans.centroids = [[2.0,2.0],[4.0,5.0]]
kmeans.mask_centroids = numpy.ones((2,2))
kmeans.cluster_assignments = [-1,-1,-1]
expected_centroids = [[2.0,4.0],[7.0,5.0]]
expected_cluster_assignments = [0,1,0]
expected_data_point_assignments = [[0,2],[1]]
expected_clustering_results = [[1,0],[0,1],[1,0]]
kmeans.cluster()
assert numpy.array_equal(expected_centroids,kmeans.centroids)
assert numpy.array_equal(expected_cluster_assignments,kmeans.cluster_assignments)
assert numpy.array_equal(expected_data_point_assignments,kmeans.data_point_assignments)
assert numpy.array_equal(expected_clustering_results,kmeans.clustering_results)
### Missing values case.
# Points 2,3,4 will first go to cluster 2, and point 1 to cluster 1.
# Then point 2 will switch to cluster 1.
X = [[2,5],[3,-1],[10,1],[-1,2]]
M = [[1,1],[1,0],[1,1],[0,1]]
K = 2
kmeans = KMeans(X,M,K)
kmeans.centroids = [[2.0,7.0],[3.0,2.0]]
kmeans.mask_centroids = numpy.ones((2,2))
kmeans.cluster_assignments = [-1,-1,-1,-1]
expected_centroids = [[2.5,5.0],[10.0,1.5]]
expected_cluster_assignments = [0,0,1,1]
expected_data_point_assignments = [[0,1],[2,3]]
expected_clustering_results = [[1,0],[1,0],[0,1],[0,1]]
kmeans.cluster()
assert numpy.array_equal(expected_centroids,kmeans.centroids)
assert numpy.array_equal(expected_cluster_assignments,kmeans.cluster_assignments)
assert numpy.array_equal(expected_data_point_assignments,kmeans.data_point_assignments)
assert numpy.array_equal(expected_clustering_results,kmeans.clustering_results)
### Cluster with 0 coordinate.
# Cluster 1 gets points 1 and 2, cluster 2 gets 3 and 4.
X = [[2,5],[3,-1],[-1,1],[-1,2]]
M = [[1,1],[1,0],[0,1],[0,1]]
K = 2
kmeans = KMeans(X,M,K)
kmeans.centroids = [[2.0,7.0],[4.0,4.0]]
kmeans.mask_centroids = numpy.ones((2,2))
kmeans.cluster_assignments = [-1,-1,-1,-1]
expected_centroids = [[2.5,5.0],[0,1.5]]
expected_cluster_assignments = [0,0,1,1]
expected_data_point_assignments = [[0,1],[2,3]]
expected_clustering_results = [[1,0],[1,0],[0,1],[0,1]]
kmeans.cluster()
assert numpy.array_equal(expected_centroids,kmeans.centroids)
assert numpy.array_equal(expected_cluster_assignments,kmeans.cluster_assignments)
assert numpy.array_equal(expected_data_point_assignments,kmeans.data_point_assignments)
assert numpy.array_equal(expected_clustering_results,kmeans.clustering_results)
def test_update():
# Normal case
X = numpy.array([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0], [7.0, 8.0, 9.0]])
M = numpy.array([[1, 1, 0], [0, 1, 0], [1, 1, 1]])
K = 2
kmeans = KMeans(X, M, K)
kmeans.data_point_assignments = numpy.array(
[[0, 1], [2]]) #points 0,1 to cluster 0, point 2 to cluster 1
kmeans.centroids = [[0.0, 0.0, 0.0], [0.0, 0.0, 0.0]]
kmeans.mask_centroids = [[0.0, 0.0, 0.0], [0.0, 0.0, 0.0]]
new_centroids = [[1.0, 3.5, 0], [7.0, 8.0, 9.0]]
new_mask_centroids = [[1, 1, 0], [1, 1, 1]]
kmeans.update()
assert numpy.array_equal(new_centroids, kmeans.centroids)
assert numpy.array_equal(new_mask_centroids, kmeans.mask_centroids)
# Case when one cluster has no points assigned to it - we then randomly re-initialise that cluster
X = numpy.array([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0], [7.0, 8.0, 9.0]])
M = numpy.array([[1, 1, 0], [0, 1, 0], [1, 1, 1]])
K = 2
kmeans = KMeans(X, M, K, 'random')
kmeans.data_point_assignments = numpy.array(
[[0, 1, 2], []]) #points 0,1,2 to cluster 0, none to cluster 1
kmeans.centroids = [[0.0, 0.0, 0.0], [0.0, 0.0, 0.0]]
kmeans.mask_centroids = [[0.0, 0.0, 0.0], [0.0, 0.0, 0.0]]
kmeans.mins = [1.0, 2.0, 9.0]
kmeans.maxs = [7.0, 8.0, 9.0]
new_centroids = [[4.0, 5.0, 9.0],
[6.066531109150288, 6.547726417641815, 9.0]]
new_mask_centroids = [[1, 1, 1], [1, 1, 1]]
random.seed(0)
kmeans.update()
assert numpy.array_equal(new_centroids, kmeans.centroids)
assert numpy.array_equal(new_mask_centroids, kmeans.mask_centroids)
# Case when we use the 'singleton' option for empty clusters - reassign point furthest away to the cluster
# Points 0 and 1 go to cluster 0, 2 to cluster 1 and none to cluster 2.
# Point 2 is furthest away, so gets reassigned to cluster 2 - making
# cluster 1 empty. Then point 1 is furthest away and gets reassigned to cluster 1
X = numpy.array([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0], [7.0, 8.0, 9.0]])
M = numpy.array([[1, 1, 0], [0, 1, 0], [1, 1, 1]])
K = 3
kmeans = KMeans(X, M, K, resolve_empty='singleton')
kmeans.data_point_assignments = numpy.array(
[[0, 1], [2],
[]]) #points 0,1 to cluster 0, 2 to cluster 1, none to cluster 2
kmeans.cluster_assignments = [0, 0, 1]
kmeans.centroids = [[1.0, 2.0, 3.0], [15.0, 16.0, 17.0],
[500.0, 500.0, 500.0]]
kmeans.mask_centroids = [[1, 1, 0], [1, 1, 1], [1, 1, 1]]
kmeans.distances = numpy.array([
kmeans.compute_MSE(kmeans.X[0], kmeans.centroids[0], M[0],
kmeans.mask_centroids[0]),
kmeans.compute_MSE(kmeans.X[1], kmeans.centroids[0], M[1],
kmeans.mask_centroids[0]),
kmeans.compute_MSE(kmeans.X[2], kmeans.centroids[1], M[2],
kmeans.mask_centroids[1])
])
kmeans.mins = [1.0, 2.0, 9.0]
kmeans.maxs = [7.0, 8.0, 9.0]
new_centroids = [[1.0, 2.0, 0], [4.0, 5.0, 6.0], [7.0, 8.0, 9.0]]
new_data_point_assignments = [[0], [1], [2]]
new_distances = [0, 0, 0]
kmeans.update()
assert new_data_point_assignments == list(kmeans.data_point_assignments)
assert numpy.array_equal(new_distances, kmeans.distances)
assert numpy.array_equal(new_centroids, kmeans.centroids)
def test_cluster():
### No missing values case.
# Points 1,2 will first go to cluster 2, and point 3 to cluster 1.
# Then point 1 will switch to cluster 1.
X = [[2, 5], [7, 5], [2, 3]]
M = numpy.ones((3, 2))
K = 2
kmeans = KMeans(X, M, K)
kmeans.centroids = [[2.0, 2.0], [4.0, 5.0]]
kmeans.mask_centroids = numpy.ones((2, 2))
kmeans.cluster_assignments = [-1, -1, -1]
expected_centroids = [[2.0, 4.0], [7.0, 5.0]]
expected_cluster_assignments = [0, 1, 0]
expected_data_point_assignments = [[0, 2], [1]]
expected_clustering_results = [[1, 0], [0, 1], [1, 0]]
kmeans.cluster()
assert numpy.array_equal(expected_centroids, kmeans.centroids)
assert numpy.array_equal(expected_cluster_assignments,
kmeans.cluster_assignments)
assert numpy.array_equal(expected_data_point_assignments,
kmeans.data_point_assignments)
assert numpy.array_equal(expected_clustering_results,
kmeans.clustering_results)
### Missing values case.
# Points 2,3,4 will first go to cluster 2, and point 1 to cluster 1.
# Then point 2 will switch to cluster 1.
X = [[2, 5], [3, -1], [10, 1], [-1, 2]]
M = [[1, 1], [1, 0], [1, 1], [0, 1]]
K = 2
kmeans = KMeans(X, M, K)
kmeans.centroids = [[2.0, 7.0], [3.0, 2.0]]
kmeans.mask_centroids = numpy.ones((2, 2))
kmeans.cluster_assignments = [-1, -1, -1, -1]
expected_centroids = [[2.5, 5.0], [10.0, 1.5]]
expected_cluster_assignments = [0, 0, 1, 1]
expected_data_point_assignments = [[0, 1], [2, 3]]
expected_clustering_results = [[1, 0], [1, 0], [0, 1], [0, 1]]
kmeans.cluster()
assert numpy.array_equal(expected_centroids, kmeans.centroids)
assert numpy.array_equal(expected_cluster_assignments,
kmeans.cluster_assignments)
assert numpy.array_equal(expected_data_point_assignments,
kmeans.data_point_assignments)
assert numpy.array_equal(expected_clustering_results,
kmeans.clustering_results)
### Cluster with 0 coordinate.
# Cluster 1 gets points 1 and 2, cluster 2 gets 3 and 4.
X = [[2, 5], [3, -1], [-1, 1], [-1, 2]]
M = [[1, 1], [1, 0], [0, 1], [0, 1]]
K = 2
kmeans = KMeans(X, M, K)
kmeans.centroids = [[2.0, 7.0], [4.0, 4.0]]
kmeans.mask_centroids = numpy.ones((2, 2))
kmeans.cluster_assignments = [-1, -1, -1, -1]
expected_centroids = [[2.5, 5.0], [0, 1.5]]
expected_cluster_assignments = [0, 0, 1, 1]
expected_data_point_assignments = [[0, 1], [2, 3]]
expected_clustering_results = [[1, 0], [1, 0], [0, 1], [0, 1]]
kmeans.cluster()
assert numpy.array_equal(expected_centroids, kmeans.centroids)
assert numpy.array_equal(expected_cluster_assignments,
kmeans.cluster_assignments)
assert numpy.array_equal(expected_data_point_assignments,
kmeans.data_point_assignments)
assert numpy.array_equal(expected_clustering_results,
kmeans.clustering_results)
